© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8274
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to finding solutions to problems and questions

    oai_token-act-pair · gemini-2.0-flash

    question answering

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     answer
    -1.34
     response
    -1.24
     Answer
    -1.12
     réponse
    -1.11
     Response
    -1.07
    answer
    -1.07
    response
    -1.06
    Answer
    -1.05
     Antwort
    -1.05
     ANSWER
    -1.05
    POSITIVE LOGITS
     <=",
    0.71
    GEBURTSDATUM
    0.62
     ModelExpression
    0.62
     кӀ
    0.61
     nahilalakip
    0.58
     wireType
    0.58
    kháu
    0.56
    الحياه
    0.56
     OFDb
    0.55
    ]=>
    0.55
    Activations Density 6.435%

    No Known Activations